Validate both YAML frontmatter formats (SKILL.md for Claude Code) and IANA-registered project.faf formats. Use when user asks "validate my skill", "check YAML format", "is my SKILL.md correct", or needs to verify format compliance for either Claude Code skills or project.faf files.
pnpm+turbo 모노레포에서 Node 버전(.nvmrc)과 터보 task 의존성을 고려해 lint/typecheck/build를 안전하게 실행하고, 실패 시 패키지 단위로 범위를 좁혀 원인을 찾습니다.
Review code changes for Jira issue. Use when the user wants to "review code", "code review", "jira review", or "check implementation".
Use when writing TypeScript code. Applies TypeScript best practices for type safety, generics, JSDoc patterns, and maintainable typed code.
hometeプロジェクト用のiOS Swiftコードレビュースキル。SwiftLintを実行し、警告・エラーを報告し、git diffで変更されたSwiftファイルをレビューする。/code-reviewコマンドでユーザーがコードレビューを要求した時、または機能実装、リファクタリング、バグ修正、テスト更新後に使用。DIパターン準拠、Swift 6並行性、過度なエンジニアリングの回避、テストコードの品質に焦点を当てる。
Use this agent when you need a final review pass to ensure code changes are as simple and minimal as possible. This agent should be invoked after implementation is complete but before finalizing changes, to identify opportunities for simplification, remove unnecessary complexity, and ensure adherence to YAGNI principles. Examples: <example>Context: The user has just implemented a new feature and wants to ensure it's as simple as possible. user: "I've finished implementing the user authentication system" assistant: "Great! Let me review the implementation for simplicity and minimalism using the code-simplicity-reviewer agent" <commentary>Since implementation is complete, use the code-simplicity-reviewer agent to identify simplification opportunities.</commentary></example> <example>Context: The user has written complex business logic and wants to simplify it. user: "I think this order processing logic might be overly complex" assistant: "I'll use the code-simplicity-reviewer agent to analyze the complexity and
Reviewt Code-Implementierungen nach Wartbarkeit, Architektur, Lesbarkeit (DDD) und sinnvoller Testabdeckung. Aktiviere bei Ticket-Abschluss, Code-Review-Anfragen, oder wenn der User nach Qualitaetspruefung fragt. Gibt nur Feedback wenn es wirklich relevant ist - kein Review um des Reviews willen.
Enforces project brand guidelines including colors, spacing, and typography from the design system. Use when creating or modifying styles, components, or design elements.
Validates Claude skill files for correct structure, YAML frontmatter, Python imports, naming conventions, and compliance with official documentation
Use this agent when reviewing code to ensure features are agent-native - that any action a user can take, an agent can also take, and anything a user can see, an agent can see. This enforces the principle that agents should have parity with users in capability and context. <example>Context: The user added a new feature to their application.\nuser: "I just implemented a new email filtering feature"\nassistant: "I'll use the agent-native-reviewer to verify this feature is accessible to agents"\n<commentary>New features need agent-native review to ensure agents can also filter emails, not just humans through UI.</commentary></example><example>Context: The user created a new UI workflow.\nuser: "I added a multi-step wizard for creating reports"\nassistant: "Let me check if this workflow is agent-native using the agent-native-reviewer"\n<commentary>UI workflows often miss agent accessibility - the reviewer checks for API/tool equivalents.</commentary></example>
Analyzes files for optimal complexity using sophistication theory - refactors code that is too simple (low entropy) or too chaotic (high entropy, low sophistication) to achieve ideal "complextropy" where code has meaningful structure without being overly complex.
Perform thorough, constructive code reviews focusing on correctness, security, maintainability, and best practices
PFLICHT bei JEDER Antwort mit Code-Änderungen! Die 8-Punkt-Checklist MUSS als ERSTES in der Response stehen. Keine Ausnahmen.
Code standards for the site. Consult when implementing features, reviewing code, refactoring, or answering questions about project conventions. Extends CLAUDE.md with type discipline, naming conventions, Astro patterns, and review checklists.
Review Rust code for idiomatic patterns, best practices, and production quality. Use when reviewing Rust crates, checking code quality, or before committing Rust changes.
Use when processing code review feedback. Technical evaluation of feedback, verify before implementing. No performative agreement or gratitude.
Analyze text for grammar, spelling, punctuation, and style issues. Execute Python script to perform detailed analysis. Use when checking grammar or proofreading.
Comprehensive code review following OWASP, SOLID, and best practices
Handle Claude Code errors gracefully - error types, recovery, prevention
コーディング規約、テスト、Lint、型チェック、後方互換性。規約、コーディング、テスト、Lint、型チェック時に使用。
Verify changes follow nearest-scoped AGENTS.md rules: group changed files by nested scope, auto-fix formatting, run lint/tests, and report violations.
Defines Android/Kotlin coding conventions for the project. Includes naming rules, forbidden patterns, preferred practices, and code style guidelines. Use when writing code to ensure consistency. Use when user mentions: 네이밍, 컨벤션, 코딩 규칙, 스타일 가이드, 금지 패턴, 권장 패턴, 이름 규칙, 코드 스타일, 컨벤션 확인, 네이밍 규칙.
